README.md

metadata

title: Phonon Reader
emoji: 🔊
colorFrom: yellow
colorTo: red
sdk: static
app_file: dist/index.html
app_build_command: npm install && npm run build
pinned: false
short_description: Text to MP3 on your device. Nothing uploaded, works offline.
models:
  - gradium/phonon-31m-en
custom_headers:
  cross-origin-embedder-policy: require-corp
  cross-origin-opener-policy: same-origin
  cross-origin-resource-policy: cross-origin

Phonon Reader

Paste an article or any text, convert it to an MP3 (or WAV), and share it to another app or save it. Speech is generated in your browser with Phonon 31m via phonon-tts (WebAssembly), and MP3 encoding runs locally with lamejs. Your text is never uploaded.

• First run downloads the model (~65 MB) from the Hub. The app shows when the app, model and voice are saved on the device; after that it works with Wi‑Fi off.
• Install it: open the Space's direct URL in Chrome on Android and choose Install app. It then shows up in the Android share sheet, so you can share selected text into it, and share the finished audio out.
• You can also just listen in the app, with the current sentence highlighted.
• Voices come from gradium/phonon-voices.

Network requests: the app files from this Space, and model/voice files from huggingface.co. Nothing else.

No bundler: npm run build copies the app, phonon-tts and the MP3 encoder into dist/ and writes the service worker's precache list. npm run serve serves dist/ locally with the isolation headers.